© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187456
    Prev
    Next
    INDEX
    Explanations

    tour, see, pope, children

    np_acts-logits-general · gemini-2.5-flash-lite

    describing states or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ু
    0.58
    is
    0.51
    или
    0.51
    者は
    0.50
    нес
    0.47
     Atau
    0.47
    或是
    0.47
    或
    0.47
    isierung
    0.45
     নিশ্চয়
    0.45
    POSITIVE LOGITS
    ]-->
    0.51
     hipp
    0.46
     slang
    0.43
    माणे
    0.42
    -->'
    0.41
    Dlg
    0.41
    Protein
    0.40
     compagnie
    0.40
     هون
    0.40
     berlaku
    0.40
    Activations Density 0.003%

    No Known Activations